From 1b8ed5e9010708808dc03681296c486737e54ab6 Mon Sep 17 00:00:00 2001
From: Martijn Vermaat <martijn@vermaat.name>
Date: Thu, 9 Jul 2015 12:14:16 +0200
Subject: [PATCH] Improve file type detection when reading DNA
---
mutalyzer/util.py | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)
diff --git a/mutalyzer/util.py b/mutalyzer/util.py
index 4a3ac13c..1ef1987f 100644
--- a/mutalyzer/util.py
+++ b/mutalyzer/util.py
@@ -357,15 +357,28 @@ def guess_file_type(handle):
"""
Guess the file type of an NGS data file.
- We assume that the stream is rewinded before use, after use, the input
- stream will be rewinded.
-
- :arg stream handle: Open readable handle to an NGS data file.
+ :arg file handle: Open readable handle to an NGS data file.
:returns unicode: Either 'fasta', 'fastq' or 'text'.
"""
+ try:
+ extension = getattr(handle, 'name').split('.')[-1]
+ except AttributeError:
+ pass
+ else:
+ if extension in ('fastq', 'fq'):
+ return 'fastq'
+ elif extension in ('fasta', 'fa'):
+ return 'fasta'
+
+ try:
+ position = handle.tell()
+ handle.seek(0)
+ except IOError:
+ return 'text'
+
token = handle.read(1)
- handle.seek(0)
+ handle.seek(position)
if token == '>':
return 'fasta'
--
GitLab